© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43327
    Prev
    Next
    INDEX
    Explanations

    decent

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the use of the adjective “decent.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hold
    -0.07
    返回
    -0.07
     Wolf
    -0.07
    jandro
    -0.07
    마사지
    -0.07
    游
    -0.07
     svět
    -0.07
    .JTable
    -0.06
    HasMaxLength
    -0.06
    لو
    -0.06
    POSITIVE LOGITS
     decent
    0.14
     respectable
    0.09
     descent
    0.09
     decency
    0.08
     insanely
    0.07
    EC
    0.07
    oon
    0.07
     convex
    0.07
     OSC
    0.07
     Kons
    0.07
    Activations Density 0.002%

    No Known Activations